Loading activity…
@balesni
Former AI alignment researcher @openai. Past: @apolloaievals, Reversal curse, Out-of-context reasoning
Technology
Ryan Greenblatt denies facilitating leaks to The Information and says he heard OpenAI accused him of reading a sensitive proposal.
AI
The Wall Street Journal reports that some researchers enabled disappearing messages in Signal chats with an outside safety researcher.
Technology
The researchers warn their firings are chilling open safety debate, while OpenAI denies retaliation.
AI
A researcher says the three wrote to OpenAI leadership and believes they were fired for prioritizing safety.
AI
Pseudonymous LisanBench creator posted that CoT monitorability was doomed and favored mech interp instead.
